1 files changed, 43 insertions, 6 deletions

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 460e90a1a0b1..34440021e8cf 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -45,6 +45,7 @@
 #include <linux/task_work.h>
 #include <linux/hardirq.h>
 #include <linux/kexec.h>
+#include <linux/vmcore_info.h>
 
 #include <asm/fred.h>
 #include <asm/cpu_device_id.h>
@@ -687,7 +688,10 @@ static noinstr void mce_read_aux(struct mce_hw_err *err, int i)
 		m->misc = mce_rdmsrq(mca_msr_reg(i, MCA_MISC));
 
 	if (m->status & MCI_STATUS_ADDRV) {
-		m->addr = mce_rdmsrq(mca_msr_reg(i, MCA_ADDR));
+		if (m->kflags & MCE_CHECK_DFR_REGS)
+			m->addr = mce_rdmsrq(MSR_AMD64_SMCA_MCx_DEADDR(i));
+		else
+			m->addr = mce_rdmsrq(mca_msr_reg(i, MCA_ADDR));
 
 		/*
 		 * Mask the reported address by the reported granularity.
@@ -715,6 +719,29 @@ static noinstr void mce_read_aux(struct mce_hw_err *err, int i)
 DEFINE_PER_CPU(unsigned, mce_poll_count);
 
 /*
+ * We have three scenarios for checking for Deferred errors:
+ *
+ * 1) Non-SMCA systems check MCA_STATUS and log error if found.
+ * 2) SMCA systems check MCA_STATUS. If error is found then log it and also
+ *    clear MCA_DESTAT.
+ * 3) SMCA systems check MCA_DESTAT, if error was not found in MCA_STATUS, and
+ *    log it.
+ */
+static bool smca_should_log_poll_error(struct mce *m)
+{
+	if (m->status & MCI_STATUS_VAL)
+		return true;
+
+	m->status = mce_rdmsrq(MSR_AMD64_SMCA_MCx_DESTAT(m->bank));
+	if ((m->status & MCI_STATUS_VAL) && (m->status & MCI_STATUS_DEFERRED)) {
+		m->kflags |= MCE_CHECK_DFR_REGS;
+		return true;
+	}
+
+	return false;
+}
+
+/*
  * Newer Intel systems that support software error
  * recovery need to make additional checks. Other
  * CPUs should skip over uncorrected errors, but log
@@ -740,6 +767,9 @@ static bool should_log_poll_error(enum mcp_flags flags, struct mce_hw_err *err)
 {
 	struct mce *m = &err->m;
 
+	if (mce_flags.smca)
+		return smca_should_log_poll_error(m);
+
 	/* If this entry is not valid, ignore it. */
 	if (!(m->status & MCI_STATUS_VAL))
 		return false;
@@ -1700,6 +1730,9 @@ noinstr void do_machine_check(struct pt_regs *regs)
 	}
 
 out:
+	/* Given it didn't panic, mark it as recoverable */
+	hwerr_log_error_type(HWERR_RECOV_OTHERS);
+
 	instrumentation_end();
 
 clear:
@@ -2410,13 +2443,13 @@ static void vendor_disable_error_reporting(void)
 	mce_disable_error_reporting();
 }
 
-static int mce_syscore_suspend(void)
+static int mce_syscore_suspend(void *data)
 {
 	vendor_disable_error_reporting();
 	return 0;
 }
 
-static void mce_syscore_shutdown(void)
+static void mce_syscore_shutdown(void *data)
 {
 	vendor_disable_error_reporting();
 }
@@ -2426,7 +2459,7 @@ static void mce_syscore_shutdown(void)
  * Only one CPU is active at this time, the others get re-added later using
  * CPU hotplug:
  */
-static void mce_syscore_resume(void)
+static void mce_syscore_resume(void *data)
 {
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info));
@@ -2434,12 +2467,16 @@ static void mce_syscore_resume(void)
 	cr4_set_bits(X86_CR4_MCE);
 }
 
-static struct syscore_ops mce_syscore_ops = {
+static const struct syscore_ops mce_syscore_ops = {
 	.suspend	= mce_syscore_suspend,
 	.shutdown	= mce_syscore_shutdown,
 	.resume		= mce_syscore_resume,
 };
 
+static struct syscore mce_syscore = {
+	.ops = &mce_syscore_ops,
+};
+
 /*
  * mce_device: Sysfs support
  */
@@ -2840,7 +2877,7 @@ static __init int mcheck_init_device(void)
 	if (err < 0)
 		goto err_out_online;
 
-	register_syscore_ops(&mce_syscore_ops);
+	register_syscore(&mce_syscore);
 
 	return 0;